Classification of the electrocardiogram signals using supervised classifiers and efficient features

Automatic classification of electrocardiogram (ECG) signals is vital for clinical diagnosis of heart disease. This paper investigates the design of an efficient system for recognition of the premature ventricular contraction from the normal beats and other heart diseases. This system includes three main modules: denoising module, feature extraction module and classifier module. In the denoising module, it is proposed the stationary wavelet transform for noise reduction of the electrocardiogram signals. In the feature extraction module a proper combination of the morphological-based features and timing interval-based features are proposed. As the classifier, several supervised classifiers are investigated; they are: a number of multi-layer perceptron neural networks with different number of layers and training algorithms, support vector machines with different kernel types, radial basis function and probabilistic neural networks. Also, for comparison the proposed features, we have considered the wavelet-based features. It has done comprehensive simulations in order to achieve a high efficient system for ECG beat classification from 12 files obtained from the MIT–BIH arrhythmia database. Simulation results show that best results are achieved about 97.14% for classification of ECG beats.